© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 19154
    Prev
    Next
    INDEX
    Explanations

    drawn-out or emphasized words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     you
    -1.81
     or
    -1.59
     on
    -1.56
    jsh
    -1.52
     to
    -1.50
     and
    -1.47
    omst
    -1.44
     Bereichen
    -1.44
    Nottingham
    -1.38
    pham
    -1.36
    POSITIVE LOGITS
    ING
    1.82
     étan
    1.63
    </i>
    1.58
     huiles
    1.51
    +};
    1.47
     falda
    1.45
    alties
    1.45
     insectes
    1.43
    re
    1.43
    越來
    1.42
    Activations Density 0.012%

    No Known Activations